Telemetry for the allow_remote_sessions capability check used by claude ultrareview now distinguishes three cases instead of collapsing them into one: a cache miss, a generic policy_disallowed reason, and a new policy_route_missing reason. This gives clearer diagnostics when ultrareview is blocked.
Names in the bundleclaude ultrareview
claude ultrareview
Claude Code changelog modified, high confidence
* Improved `/ultrareview` and `claude ultrareview` to wait up to 45 minutes (previously 30) for long-running cloud reviewssee the edit
claude ultrareview
Week 18 · April 27 – May 1, 2026 modified, high confidence
<div>New <a href="/docs/en/ultrareview"><code>claude ultrareview</code></a> subcommand runs <code>/ultrareview</code> non-interactively from CI or scripts: prints findings to stdout (<code>--json</code> for raw output) and exits 0 on compl…see the edit
The entry above is what we published on the day. These lines were added later, as Anthropic's own pages caught up, and they sit beside the original rather than replacing it.
Added since
A small documentation edit on Code Review touched a line naming claude ultrareview after this was published.
To run a cloud review from a script or CI job, use the [`claude ultrareview` subcommand](/docs/en/ultrareview#run-ultrareview-non-interactively), which waits for the findings and prints them to stdout.code-review see the edit
Confirmed since
Anthropic's documentation has since written up claude ultrareview, on CLI reference.
| `claude ultrareview [target]` | Run [ultrareview](/docs/en/ultrareview#run-ultrareview-non-interactively) non-interactively. Prints findings to stdout and exits 0 on success or 1 on failure. Use `--json` for the raw payload and `--timeou…cli-reference see the edit
One source agreesOne thing we can check says the same as this entry.
Anthropic's documentation agrees
claude ultrareview on Claude Code changelog